{"list":"other","total":89,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2210.03629","title":"ReAct: Synergizing Reasoning and Acting in Language Models","created":"2022-10-06","cited_by_count":8695},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1806.07366","title":"Neural Ordinary Differential Equations","created":"2018-06-19","cited_by_count":3779},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2308.11432","title":"A Survey on Large Language Model based Autonomous Agents","created":"2023-08-22","cited_by_count":2242},{"id":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"2209.15571","title":"Building Normalizing Flows with Stochastic Interpolants","created":"2022-09-30","cited_by_count":995},{"id":"2103.01955","title":"The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games","created":"2021-03-02","cited_by_count":942},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"2209.07858","title":"Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned","created":"2022-08-23","cited_by_count":729},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1905.13319","title":"MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms","created":"2019-05-30","cited_by_count":662},{"id":"2004.03685","title":"Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?","created":"2020-04-07","cited_by_count":599},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"1806.00069","title":"Explaining Explanations: An Overview of Interpretability of Machine Learning","created":"2018-05-31","cited_by_count":508},{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"2404.10719","title":"Is DPO Superior to PPO for LLM Alignment? A Comprehensive Study","created":"2024-04-16","cited_by_count":262},{"id":"2209.02646","title":"A Survey on Generative Diffusion Model","created":"2022-09-06","cited_by_count":240},{"id":"2401.08967","title":"ReFT: Reasoning with Reinforced Fine-Tuning","created":"2024-01-17","cited_by_count":239},{"id":"2407.19594","title":"Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge","created":"2024-07-28","cited_by_count":204},{"id":"1804.02477","title":"Programmatically Interpretable Reinforcement Learning","created":"2018-04-06","cited_by_count":193},{"id":"1612.07182","title":"Multi-Agent Cooperation and the Emergence of (Natural) Language","created":"2016-12-21","cited_by_count":185},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"2309.10062","title":"SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models","created":"2023-09-18","cited_by_count":153},{"id":"2004.14546","title":"WT5?! Training Text-to-Text Models to Explain their Predictions","created":"2020-04-30","cited_by_count":148},{"id":"2311.09528","title":"HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM","created":"2023-11-16","cited_by_count":142},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"1310.0150","title":"Stability","created":"2013-10-01","cited_by_count":120},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113},{"id":"2307.11768","title":"Question Decomposition Improves the Faithfulness of Model-Generated Reasoning","created":"2023-07-17","cited_by_count":108},{"id":"2312.02139","title":"DiffiT: Diffusion Vision Transformers for Image Generation","created":"2023-12-04","cited_by_count":106},{"id":"2401.07927","title":"Are self-explanations from Large Language Models faithful?","created":"2024-01-15","cited_by_count":101},{"id":"2309.00779","title":"Value Kaleidoscope: Engaging AI with Pluralistic Human Values, Rights, and Duties","created":"2023-09-02","cited_by_count":97},{"id":"1901.03729","title":"Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions","created":"2019-01-11","cited_by_count":81},{"id":"2102.02201","title":"When Can Models Learn From Explanations? A Formal Framework for Understanding the Roles of Explanation Data","created":"2021-02-03","cited_by_count":75},{"id":"2311.07466","title":"On Measuring Faithfulness or Self-consistency of Natural Language Explanations","created":"2023-11-13","cited_by_count":73},{"id":"2408.02666","title":"Self-Taught Evaluators","created":"2024-08-05","cited_by_count":72},{"id":"1602.02658","title":"Graying the black box: Understanding DQNs","created":"2016-02-08","cited_by_count":68},{"id":"1807.05887","title":"Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees","created":"2018-07-16","cited_by_count":65},{"id":"2305.09863","title":"Explaining black box text modules in natural language with language models","created":"2023-05-17","cited_by_count":62},{"id":"1912.05743","title":"Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning","created":"2019-12-09","cited_by_count":60},{"id":"2210.09292","title":"Efficient Diffusion Models for Vision: A Survey","created":"2022-10-07","cited_by_count":51},{"id":"2305.11426","title":"Post Hoc Explanations of Language Models Can Improve Language Models","created":"2023-05-19","cited_by_count":50},{"id":"1803.07517","title":"Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges","created":"2018-03-20","cited_by_count":49},{"id":"1712.04170","title":"Interpretable Policies for Reinforcement Learning by Genetic Programming","created":"2017-12-12","cited_by_count":48},{"id":"1810.08174","title":"Establishing Appropriate Trust via Critical States","created":"2018-10-18","cited_by_count":48},{"id":"2103.12279","title":"SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers","created":"2021-03-23","cited_by_count":44},{"id":"2002.03478","title":"Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions","created":"2020-02-10","cited_by_count":41},{"id":"1811.12530","title":"Learning Finite State Representations of Recurrent Policy Networks","created":"2018-11-29","cited_by_count":37},{"id":"1905.12044","title":"Generation of Policy-Level Explanations for Reinforcement Learning","created":"2019-05-28","cited_by_count":37},{"id":"2411.11984","title":"Understanding Chain-of-Thought in LLMs through Information Theory","created":"2024-11-18","cited_by_count":37},{"id":"2402.03659","title":"Learning to Generate Explainable Stock Predictions using Self-Reflective Large Language Models","created":"2024-02-06","cited_by_count":36},{"id":"2011.05268","title":"Towards Interpretable Natural Language Understanding with Explanations as Latent Variables","created":"2020-10-24","cited_by_count":30},{"id":"2402.09764","title":"Aligning Crowd Feedback via Distributional Preference Reward Modeling","created":"2024-02-15","cited_by_count":28},{"id":"2106.02097","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","created":"2021-06-03","cited_by_count":27},{"id":"2407.08348","title":"Skywork-Math: Data Scaling Laws for Mathematical Reasoning in Large Language Models -- The Story Goes On","created":"2024-07-11","cited_by_count":24},{"id":"2009.04743","title":"TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments","created":"2020-09-10","cited_by_count":18},{"id":"2006.03745","title":"Re-understanding Finite-State Representations of Recurrent Policy Networks","created":"2020-06-06","cited_by_count":15},{"id":"2006.04109","title":"Incorporating Pragmatic Reasoning Communication into Emergent Language","created":"2020-06-07","cited_by_count":15},{"id":"2402.08277","title":"Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering","created":"2024-02-13","cited_by_count":11},{"id":"2412.20800","title":"VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control","created":"2024-12-30","cited_by_count":9},{"id":"1912.04078","title":"Reinforcement Learning-based Visual Navigation with Information-Theoretic Regularization","created":"2019-12-09","cited_by_count":7},{"id":"2304.12958","title":"A Closer Look at Reward Decomposition for High-Level Robotic Explanations","created":"2023-04-25","cited_by_count":7},{"id":"2410.13953","title":"On Diffusion Models for Multi-Agent Partial Observability: Shared Attractors, Error Bounds, and Composite Flow","created":"2024-10-17","cited_by_count":5},{"id":"2306.09273","title":"Privacy Risks in Reinforcement Learning for Household Robots","created":"2023-06-15","cited_by_count":4}],"next_cursor":null}